Andreas Mohr, M.Sc.

Adresse

Technische Universität Hamburg
Institut für Maritime Logistik
Am Schwarzenberg-Campus 4 (D)
21073 Hamburg

 

Kontaktdaten

Büro: Gebäude D Raum 5.006
Tel.: +49 40 42878 4641
E-Mail: andreas.mohr(at)tuhh(dot)de
ORCiD: 0000-0001-8751-4052



Forschungsschwerpunkte

  • Binnen- und Seehafen-Containerterminals
  • Elektrifizierung des Horizontalverkehrs in Containerterminals
  • Containerterminal- und Hafeninterne Containertransporte
  • Entwicklung und Digitalisierung der maritimen Lehre
  • Ereignisorientierte Simulation


Veröffentlichungen (Auszug)

2023
[186601]
Title: AI Approaches in Education Based on Individual Learner Characteristics: A Review. <em>2023 IEEE 12th International Conference on Engineering Education (ICEED)</em>
Written by: Grasse, Ole and Mohr, Andreas and Lange, Ann-Kathrin and Jahn, Carlos
in: (2023).
Volume: Number:
on pages: 50--55
Chapter:
Editor:
Publisher: IEEE:
Series:
Address:
Edition:
ISBN: 979-8-3503-0742-9
how published:
Organization:
School:
Institution:
Type:
DOI: 10.1109/ICEED59801.2023.10264043
URL: https://ieeexplore.ieee.org/document/10264043
ARXIVID:
PMID:

[pdf] [www]

Note: GENERATING

Abstract: The number of students who demand high quality education is growing continuously. Targeted, efficient education becomes increasingly important. Digital teaching formats combined with artificial intelligence offer promising opportunities and provide insights to develop seminal educational systems. In an ideal world the necessary data mining is integrated in those approaches and does not require sensors, surveillance or the close supervision of teachers. This review paper investigates the current state of research regarding actual applications of AI in educational learning concepts together with a focus on individual learner characteristics data. Within the study, 1.025 scientific papers from Scopus where screened and filtered. 67 papers were finally classified and evaluated. The review takes a close look at identified application categories such as the educational level of learners, academic subjects considered, learning environments used, types and objectives of the AI approaches, as well as a detailed examination of the underlying data. The actuality of the “AI in Education” topic is clearly visible in the growing number of publications. A substantial proportion of applications focus on university education with an accumulation in STEM subjects. Often, supervised AI approaches are used which focus on the prediction of learner performances. Data-wise, we see a lot of similarities in the approaches together with opportunities for improvement in terms of transparency and standardization.